I also made some pages (around a decade ago) which implement various optimisation algorithms, including GA (with just mutation, with just crossover, and with both). The task they're solving is less interesting though: find the brightest point on a randomly-generated image. In fact, being so low-dimensional, the enumeration algorithm is probably the best choice!

http://www.chriswarbo.net/projects/optimisation

I think it's interesting and deserves a longer dive, particularly in car representation and crossover/mutation functions, as well as:

> The optimality of a particular candidate solution (the fitness function) is determined by how far it travels before a) a mass touches the ground or b) time runs out.

How do you sort among the millions of possible solutions that automatically die upon touching ground.

This was great, thanks! Really enjoyed this

Do you have some resources for someone who wants to start to build their own version and/or some other GA?

bro, your cert is expired. just a friendly reminder.

Can't stop watching.